Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25cf1d4db2332b67dfddefaf322529253dd6ea71971877e2e5e5bbac2a229c50
+oid sha256:5716d1bbc8d09e04b40a0f363d9887fb471e612414a7d1e33045df223847b4e3
 size 116795404

run-8/checkpoint-1100/config.json

@@ -0,0 +1,54 @@
+{
+  "_name_or_path": "cointegrated/rubert-tiny2",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "emb_size": 312,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 312,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 600,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 2048,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 3,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 83828
+}

run-8/checkpoint-1100/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57881509ca030ca12944ba7b7bd43f98fadbdaf158c3bf42c17d65b6bea54251
+size 116795404

run-8/checkpoint-1100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0ed9bf440fe6baf9713ec433d66f61a9545f84a5c322c98668e9bccc24c869e
+size 233621882

run-8/checkpoint-1100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3180da2883c56c8e0a6a790414652de70473fb9817815bef9e488338d650da67
+size 13990

run-8/checkpoint-1100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c6acc11546822efd94202c78e6de1055350d78d6f5509d86b51f9a734699245
+size 1064

run-8/checkpoint-1100/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

run-8/checkpoint-1100/tokenizer_config.json

@@ -0,0 +1,64 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 2048,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

run-8/checkpoint-1100/trainer_state.json

@@ -0,0 +1,56 @@
+{
+  "best_metric": 0.8448979591836735,
+  "best_model_checkpoint": "rubert-tiny2-finetuned-classification\\run-8\\checkpoint-1100",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1100,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.33127981814863e-05,
+      "loss": 1.7493,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7346938775510204,
+      "eval_loss": 1.10899817943573,
+      "eval_runtime": 1.157,
+      "eval_samples_per_second": 211.754,
+      "eval_steps_per_second": 13.829,
+      "step": 550
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 2.2187996969143835e-06,
+      "loss": 1.0489,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8448979591836735,
+      "eval_loss": 0.860304057598114,
+      "eval_runtime": 1.1,
+      "eval_samples_per_second": 222.727,
+      "eval_steps_per_second": 14.545,
+      "step": 1100
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1100,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 1918563271800.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.4406796666058216e-05,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 4,
+    "seed": 23
+  }
+}

run-8/checkpoint-1100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21515c0aee4d3f4dc59057e98dcd8f5a11a85c9d1a2b970eab3ec758ada28202
+size 4728

runs/Jan15_00-51-52_DESKTOP-RFEED41/events.out.tfevents.1705262400.DESKTOP-RFEED41.20976.14

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f289b11e547bd71932bc28d1b4ae57102c03994fa57c6e65baa5b166da074ace
-size 5589
+oid sha256:939990a93aae57d807d367969c40cb4698f403dc8717531cfe60812532078aff
+size 6266

runs/Jan15_00-51-52_DESKTOP-RFEED41/events.out.tfevents.1705262836.DESKTOP-RFEED41.20976.15

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c65c4b56ac88fd9474b75e61f79f70fc9bcb7d0d28716eaf3ea540cfe99aa97
+size 5275

runs/Jan15_03-24-24_DESKTOP-RFEED41/events.out.tfevents.1705263884.DESKTOP-RFEED41.25704.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29d31213a557775abee5070c66830ed3e0f51a7cdaf1ad9a021c4515370d396b
+size 5582

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21515c0aee4d3f4dc59057e98dcd8f5a11a85c9d1a2b970eab3ec758ada28202
+oid sha256:b90b76663031bfc80999460662f900aee143d2aeea6b089afbfa4ec24c2c5a76
 size 4728